Geekbench AI Score

2021
Single Precision Score
1994
Half Precision Score
2892
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date August 22 2025 08:25 AM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 15
Model Samsung Galaxy S24 Ultra
Model IDsamsung SM-S928B
Motherboard pineapple
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.40 GHz
Memory Information
Size 10.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1673
311.1 IPS
 
Image Classification (HP)
100% 1791
333.1 IPS
 
Image Classification (Q)
100% 2899
539.2 IPS
 
Image Segmentation (SP)
100% 2329
37.8 IPS
 
Image Segmentation (HP)
100% 2278
36.9 IPS
 
Image Segmentation (Q)
98% 3605
58.6 IPS
 
Pose Estimation (SP)
100% 4247
4.96 IPS
 
Pose Estimation (HP)
100% 3322
3.88 IPS
 
Pose Estimation (Q)
84% 6214
7.37 IPS
 
Object Detection (SP)
98% 1267
100.9 IPS
 
Object Detection (HP)
98% 1258
100.1 IPS
 
Object Detection (Q)
83% 1756
141.9 IPS
 
Face Detection (SP)
100% 2703
32.1 IPS
 
Face Detection (HP)
100% 2601
30.9 IPS
 
Face Detection (Q)
95% 4309
51.4 IPS
 
Depth Estimation (SP)
99% 2836
21.9 IPS
 
Depth Estimation (HP)
99% 2842
22.0 IPS
 
Depth Estimation (Q)
64% 4321
39.6 IPS
 
Style Transfer (SP)
89% 6809
8.84 IPS
 
Style Transfer (HP)
89% 6753
8.77 IPS
 
Style Transfer (Q)
98% 12691
16.4 IPS
 
Image Super-Resolution (SP)
100% 1354
50.0 IPS
 
Image Super-Resolution (HP)
100% 1435
53.0 IPS
 
Image Super-Resolution (Q)
97% 3144
116.5 IPS
 
Text Classification (SP)
100% 532
710.3 IPS
 
Text Classification (HP)
99% 590
787.4 IPS
 
Text Classification (Q)
88% 852
1.15 KIPS
 
Machine Translation (SP)
100% 1444
24.9 IPS
 
Machine Translation (HP)
100% 1385
23.9 IPS
 
Machine Translation (Q)
50% 568
20.2 IPS
 

Compare

Set Baseline Geekbench 6 now available